API docs / Video models
Wan 2.6 Flash API
Generates videos with optional synchronized audio from a single input image and text prompt. This flash variant of Alibaba Tongyi Lab's Wan2.6 model prioritizes speed while maintaining visual quality, creating up to 15 seconds of video at 720p or 1080p resolution. Features native audio-visual synchronization that can generate matching sound effects and ambient atmosphere, or sync with uploaded audio files. Supports multi-shot narrative segmentation for creating varied content within a single generation. Maintains consistent visuals throughout clips with smooth motion at 24 frames per second. Includes prompt expansion optimization and negative prompting for refined control over generation. Suitable for marketing concept testing, educational content creation, social media posts, and creative projects requiring quick turnaround times.
- Model id
wan-video/wan2.6-i2v-flash- Provider
- wan-video
- Output
- Video
- Price
- From 88 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "wan-video/wan2.6-i2v-flash". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "wan-video/wan2.6-i2v-flash",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light",
"first_frame": [
"https://example.com/input.png"
]
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
promptrequired | string | Text prompt for video generation |
first_framerequired | array of URLs | Input image for video generation Up to 1 files · Accepts image/* |
reference_audios | array of URLs | Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization Each file: 3–30s. Each file: up to 15 MB. Up to 1 files · Accepts audio/* |
resolution | string | Default: One of: 720p, 1080p |
duration_seconds | number | Default: One of: 5, 10, 15 |
generate_audio | boolean | Whether to generate video with audio. When enabled, the model will auto-generate audio or use provided audio file. Disable for silent video output. Default: |
enhance_prompt | boolean | If set to true, the prompt optimizer will be enabled Default: |
seed | number | Random seed for reproducible generation |
negative_prompt | string | Negative prompt to avoid certain elements Default: |
multi_shots | boolean | Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content. Default: |